[Model]: LateOn
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.2k
- Forks
- 248
- Avg merge
- 4d 8h
- Merged PRs (30d)
- 4
Description
Which model would you like to support?
https://huggingface.co/lightonai/LateOn
What are the main advantages of this model?
Beats every existing ColBERT model, including those 4× its size (Jina ColBERT v2 at 559M, Arctic Embed L v2 at 568M).
Holds up under decontamination: when training-overlap samples are stripped from the BEIR corpora, LateOn climbs to 60.36 nDCG@10 on the 12-dataset decontaminated split — first place overall.
Uses fully open data for both pre-training and fine-tuning, with all signals released as metadata so you can rebuild, extend, or replace any filter.
https://x.com/antoine_chaffin/status/2060845436378783970?s=20
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the LateOn model page at https://huggingface.co/lightonai/LateOn and the existing model-support patterns in fastembed. Determine the integration and validation work needed for this model; done means LateOn is available through fastembed and its support is covered by appropriate checks.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- huggingface, python
- Domain
- machine-learning, search
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100